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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "come" followed by conjunctions or verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing invitations and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.65
     pseudonym
    -0.64
    iction
    -0.62
    STE
    -0.60
     reliance
    -0.58
    808
    -0.58
    ylon
    -0.57
    immune
    -0.56
    omi
    -0.56
    ingo
    -0.56
    POSITIVE LOGITS
    uin
    0.78
    rew
    0.76
    romeda
    0.72
    rogen
    0.71
     forth
    0.69
     kissed
    0.69
     inspect
    0.68
     groom
    0.67
     greet
    0.67
    aped
    0.67
    Act Density 0.101%

    No Known Activations