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

    Neuronpedia

    INDEX
    Explanations

    references to blog posts and comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regar
    -0.16
     Weiner
    -0.15
    į°
    -0.14
    ufe
    -0.14
    olet
    -0.14
    .management
    -0.14
    htm
    -0.14
    terra
    -0.14
    TEE
    -0.13
    izm
    -0.13
    POSITIVE LOGITS
     Leave
    0.42
    Leave
    0.36
     leave
    0.31
    leave
    0.27
    _leave
    0.25
     leaves
    0.22
     çķĻ
    0.22
    çķĻ
    0.21
    .leave
    0.20
     leaving
    0.19
    Act Density 0.030%

    No Known Activations