Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving and helpfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a negation or qualification

    np_acts-logits-general · gemini-2.0-flash

    at least not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.77
    DebuggerNonUser
    -0.74
    Hochspringen
    -0.72
    InvalidProtocol
    -0.69
    IVEREF
    -0.68
    VersionUID
    -0.67
    DockStyle
    -0.67
    plevel
    -0.66
     onAnimation
    -0.65
    mappedBy
    -0.64
    POSITIVE LOGITS
     albeit
    0.70
    ish
    0.68
     ish
    0.65
     insofar
    0.63
    albeit
    0.63
     until
    0.56
    until
    0.55
     indirectly
    0.55
     vaguely
    0.54
    sor
    0.52
    Act Density 0.218%

    No Known Activations