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

    Neuronpedia

    INDEX
    Explanations

    phrases and discussions around value, comparisons, and convincing arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerStep
    -0.59
    PhysRevLett
    -0.59
     tarko
    -0.56
    parsedMessage
    -0.56
     Meksiku
    -0.56
    GrantedAuthority
    -0.55
    -0.54
    ImageContext
    -0.54
    InitVars
    -0.53
     familières
    -0.52
    POSITIVE LOGITS
     surprisingly
    0.91
     remarkably
    0.82
     fairly
    0.78
     relatively
    0.76
     pretty
    0.74
    relatively
    0.73
    Surprisingly
    0.73
     Fairly
    0.71
    pretty
    0.71
    意外と
    0.70
    Act Density 0.215%

    No Known Activations