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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to seeking help or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.62
    SafeMath
    -0.53
     contextLoads
    -0.51
    URLException
    -0.48
    UIControlState
    -0.47
    GEBURTSDATUM
    -0.47
    inSlope
    -0.44
    помним
    -0.44
     endwhile
    -0.43
    Melan
    -0.42
    POSITIVE LOGITS
     me
    3.98
    me
    1.94
     мне
    1.85
     mnie
    1.82
     меня
    1.82
     myself
    1.81
     comigo
    1.73
     Me
    1.66
     conmigo
    1.63
    ándome
    1.57
    Act Density 1.317%

    No Known Activations